Data Scientist - Advanced Analytics

Description :

Experience Required : 6+ years total (2+ years relevant in RAG / LLM-based systems)

Location : Open / Any Location (India)

Employment Type : Full-time

Role Overview :

We are looking for an experienced Data Scientist Advanced Analytics with strong expertise in Python, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) systems. The ideal candidate will be responsible for designing, building, and optimizing intelligent retrieval systems that combine LLM reasoning with real-time document understanding.

Key Responsibilities :

- Design and implement Retrieval-Augmented Generation (RAG) pipelines and architectures.

- Develop document retrieval, contextual augmentation, and chunking strategies for large-scale unstructured data.

- Work with embedding models and vector databases such as FAISS, Pinecone, Weaviate, ChromaDB, or Milvus.

- Optimize RAG indexing, retrieval accuracy, and context relevance using advanced evaluation metrics.

- Implement fine-tuning and prompt engineering techniques to improve retrieval and generation quality.

- Manage token limits, context windows, and retrieval latency for high-performance inference.

- Integrate LLM frameworks like LangChain or LlamaIndex for pipeline orchestration.

- Utilize APIs from OpenAI, Hugging Face Transformers, or other LLM providers for model integration.

- Perform noise reduction, diversity sampling, and retrieval optimization to enhance output reliability.

- Collaborate with cross-functional teams to deploy scalable RAG-based analytics solutions.

Required Skills & Experience :

- Programming : Strong hands-on experience with Python.

- RAG Expertise : In-depth understanding of RAG pipelines, RAG architecture, and retrieval optimization.

- Vector Databases : Practical experience with FAISS, Pinecone, Weaviate, ChromaDB, or Milvus.

- Embedding Models : Knowledge of generating and fine-tuning embeddings for semantic search and document retrieval.

- LLM Tools : Experience with LangChain, LlamaIndex, OpenAI API, and Hugging Face Transformers.

- Optimization : Strong understanding of token/context management, retrieval latency, and inference efficiency.

- Evaluation Metrics : Familiarity with Retrieval Accuracy, Context Relevance, and Answer Faithfulness.

Good to Have :

- Experience in MLOps for deploying and monitoring LLM/RAG-based solutions.

- Understanding of semantic search algorithms and context ranking models.

- Exposure to knowledge retrieval, contextual augmentation, or multi-document summarization.

- Masters degree in Computer Science, Artificial Intelligence, Data Science, or related field.

What Youll Get :

- Opportunity to work with cutting-edge LLM and RAG technologies.

- Exposure to complex, real-world AI and data engineering challenges.

- Continuous learning, experimentation, and innovation in Generative AI and retrieval optimization.